PAUL is a structured development workflow for Claude Code that organizes AI-assisted work into planning, implementation, and state-reconciliation steps. It is for developers who want acceptance criteria, managed context, and completed plans while building software with Claude Code. Its catalogue entries are commands that implement the workflow.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/christopherkahler/paul/handoffgit clone --depth 1 https://github.com/ChristopherKahler/paulWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/christopherkahler/paul/handoff)<a href="https://agentmods.dev/commands/christopherkahler/paul/handoff"><img src="https://agentmods.dev/badge/commands/christopherkahler/paul/handoff.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00012 | $0.01367 |
| Opus 5 | $0.00006 | $0.00683 |
| Sonnet 5 | $0.00002 | $0.00273 |
| Haiku 4.5 | $0.00001 | $0.00137 |
Grade A, and why
paul:handoff scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use: End of session, context break, or when decisions need documentation.
Smart context: Uses conversation context for decisions/gaps. Optional argument for additional notes.
<execution_context> @.paul/STATE.md </execution_context>
Session context is primary source - extract:
- What was accomplished (file changes, plans executed)
- Decisions made (explicit or implicit in conversation)
- Questions asked and answered
- Gaps identified
- User's stated intentions
From conversation context:
- Files created/modified this session
- Commands executed
- Decisions discussed (look for "I want", "let's do", "decision:", user preferences)
- Questions raised (look for "?", "should we", "what about")
- Gaps identified (look for "missing", "need", "gap", "TODO")
- User's stated approach/thoughts
From optional $ARGUMENTS:
- Additional context user provided inline
- Override or supplement detected context
-
Session Accomplishments:
- What was built/completed
- Plans executed
- Files created
-
Decisions Made:
- Explicit decisions from conversation
- Implicit decisions (choices made without discussion)
- Rationale where stated
-
Gap Analysis:
- Issues identified
- User's decision on each gap
- Effort estimates if discussed
-
Open Questions:
- Unresolved items
- Items needing more discussion
-
Reference Files:
- Files mentioned that will be needed
- Source files for next session
# PAUL Session Handoff
**Session:** {date} {start_time} - {end_time}
**Phase:** {current_phase}
**Context:** {brief description}
---
## Session Accomplishments
{bulleted list of what was done}
---
## Decisions Made
| Decision | Rationale | Impact |
|----------|-----------|--------|
| {decision} | {why} | {effect} |
---
## Gap Analysis with Decisions
### {Gap Name}
**Status:** CREATE / DEFER / INTENTIONAL
**Notes:** {user's decision and reasoning}
**Effort:** {if discussed}
**Reference:** `@{source_file}`
---
## Open Questions
{items needing resolution}
---
## Reference Files for Next Session
{list of @-references}
---
## Prioritized Next Actions
| Priority | Action | Effort |
|----------|--------|--------|
| 1 | {action} | {effort} |
---
## State Summary
**Current:** {phase, plan, loop position}
**Next:** {recommended next action}
**Resume:** `/paul:resume` then read this handoff
---
*Handoff created: {timestamp}*
Display confirmation:
════════════════════════════════════════
HANDOFF CREATED
════════════════════════════════════════
Saved: .paul/HANDOFF-{date}-{context}.md
Includes:
- {N} accomplishments
- {N} decisions documented
- {N} gaps with your decisions
- {N} prioritized next actions
Next session: /paul:resume → read handoff
════════════════════════════════════════
Without this, the doc sits on disk but the session-start resume list never queues it (the gap that loses handoffs). The project slug comes from .paul/paul.toml's name field; the doc path must be absolute.
if command -v base >/dev/null 2>&1; then
PROJECT=$(grep -m1 '^name *= *' .paul/paul.toml 2>/dev/null | sed -E 's/^name *= *"(.*)"/\1/')
DOC="$(pwd)/.paul/HANDOFF-{date}-{context}.md"
if [ -n "$PROJECT" ] && [ -f "$DOC" ]; then
base handoff create --project "$PROJECT" --doc "$DOC" \
&& echo "✓ Registered with base — resurfaces at next session start" \
|| echo "Note: base handoff registration skipped (pre-handoff base version)"
fi
fi
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 223 lines · 12 tokens per session scan A f535e594f768
paul:handoff is a command published in the GitHub repository ChristopherKahler/paul (1,212 stars, last pushed 13d ago), licensed MIT. It adds 12 tokens to every session and 1,367 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
safe-refactor
Safe refactoring with automated review, testing, and rollback capabilities.
security-review
Comprehensive security analysis with multi-layer vulnerability detection.
test
Smart test runner with filtering, coverage, and health monitoring.
implement-spec
Implement specification with full traceability and test-driven development.
refactor
Interactive refactoring assistant based on Martin Fowler's refactoring catalog.
deploy_to_docker
Build Docker image and start/redeploy the MCP Task Orchestrator container, reusing the last-used config by default.